2112 Commits

Author SHA1 Message Date
Robin Huang
2faa9f7f51 Add lora. 2024-04-02 16:02:06 -07:00
Robin Huang
1cac373d8f Switch back to use @main 2024-04-02 14:44:58 -07:00
Robin Huang
eee7b4c122 Use linux branch. 2024-04-02 14:02:00 -07:00
Robin Huang
ac8d26a04e Add paths ignore. 2024-04-02 13:52:39 -07:00
Robin Huang
09ddcd22be Update. 2024-04-02 10:51:13 -07:00
Robin Huang
c70847d0e6 Update. 2024-04-02 10:38:45 -07:00
Robin Huang
bedc2767e1 Run with m2. 2024-04-01 11:44:19 -07:00
Robin Huang
99c807aac7 Upload. 2024-04-01 11:06:52 -07:00
Robin Huang
6a3b2238d2
Merge branch 'comfyanonymous:master' into master 2024-04-01 10:38:47 -07:00
comfyanonymous
1306464538 --force-fp16 is no longer necessary on Mac. 2024-03-31 12:50:28 -04:00
comfyanonymous
575acb69e4 IP2P model loading support.
This is the code to load the model and inference it with only a text
prompt. This commit does not contain the nodes to properly use it with an
image input.

This supports both the original SD1 instructpix2pix model and the
diffusers SDXL one.
2024-03-31 03:10:28 -04:00
comfyanonymous
96b4c757cf Add log to debug custom nodes that hang when imported. 2024-03-30 11:52:11 -04:00
Robin Huang
34690f544f 50 second timeout. 2024-03-29 19:01:31 -07:00
Robin Huang
d11f6a4b70 Use xlarge runner. 2024-03-29 18:40:33 -07:00
Robin Huang
025b871ebe Timeout. 2024-03-29 18:16:37 -07:00
Robin Huang
b3d5c667c4 Unpin python. 2024-03-29 13:53:13 -07:00
comfyanonymous
94a5a67c32 Cleanup to support different types of inpaint models. 2024-03-29 14:44:13 -04:00
Robin Huang
79ff76fceb Update test workflow. 2024-03-29 11:35:03 -07:00
comfyanonymous
9bf6061dfc Switch prints to logging in folder_paths and add some extra debug. 2024-03-29 03:07:13 -04:00
Robin Huang
ffd3e3a8ce Add workflow json to run. 2024-03-28 20:19:40 -07:00
Robin Huang
90252bfc08 Put some model. 2024-03-28 16:29:15 -07:00
comfyanonymous
5d8898c056 Fix some performance issues with weight loading and unloading.
Lower peak memory usage when changing model.

Fix case where model weights would be unloaded and reloaded.
2024-03-28 18:04:42 -04:00
Robin Huang
30d2f38247 Manual trigger. 2024-03-28 14:47:06 -07:00
Robin Huang
684c04c83d Add macos CI. 2024-03-28 14:41:58 -07:00
comfyanonymous
327ca1313d Support SDXS 0.9 2024-03-27 23:58:58 -04:00
comfyanonymous
8ae1e4d125 Make step on sharpen node smaller. 2024-03-27 01:28:31 -04:00
comfyanonymous
2f93b91646 Add Tesla GPUs to cuda malloc blacklist. 2024-03-26 23:09:28 -04:00
comfyanonymous
c9673926fb Fix test. 2024-03-26 04:07:30 -04:00
comfyanonymous
11838e60f4 Increase the max resolution. 2024-03-26 04:00:53 -04:00
comfyanonymous
ae77590b4e dora_scale support for lora file. 2024-03-25 18:09:23 -04:00
comfyanonymous
c6de09b02e Optimize memory unload strategy for more optimized performance. 2024-03-24 02:36:30 -04:00
comfyanonymous
6a32c06f06 Move cleanup_models to improve performance. 2024-03-23 17:27:10 -04:00
comfyanonymous
a28a9dc836 Add an example to use the SaveImageWebsocket node and enable it. 2024-03-22 12:56:48 -04:00
comfyanonymous
0624838237 Add inverse noise scaling function. 2024-03-21 14:49:11 -04:00
comfyanonymous
5d875d77fe Fix regression with lcm not working with batches. 2024-03-20 20:48:54 -04:00
comfyanonymous
4b9005e949 Fix regression with model merging. 2024-03-20 13:56:12 -04:00
comfyanonymous
c18a203a8a Don't unload model weights for non weight patches. 2024-03-20 02:27:58 -04:00
comfyanonymous
150a3e946f Make LCM sampler use the model noise scaling function. 2024-03-20 01:35:59 -04:00
comfyanonymous
d14bdb1896 Revert, NOTE: this will be removed again soon please fix your nodes. 2024-03-19 11:17:49 -04:00
comfyanonymous
0c55f16c9e Remove code that should be useless now. 2024-03-19 09:47:14 -04:00
comfyanonymous
40e124c6be SV3D support. 2024-03-18 16:54:13 -04:00
comfyanonymous
0b78213bda Fix neg scale step. 2024-03-18 15:51:23 -04:00
comfyanonymous
b1a16d4500 Fix stable cascade img2img not working with all resolutions. 2024-03-18 13:51:38 -04:00
comfyanonymous
cacb022c4a Make saved SD1 checkpoints match more closely the official one. 2024-03-18 00:26:23 -04:00
comfyanonymous
d3406d8d58 Increase image batch nodes maximum values. 2024-03-17 08:57:49 -04:00
comfyanonymous
d7897fff2c Move cascade scale factor from stage_a to latent_formats.py 2024-03-16 14:49:35 -04:00
comfyanonymous
f2fe635c9f SamplerDPMAdaptative node to test the different options. 2024-03-15 22:36:10 -04:00
comfyanonymous
448d9263a2 Fix control loras breaking. 2024-03-14 09:30:21 -04:00
comfyanonymous
db8b59ecff Lower memory usage for loras in lowvram mode at the cost of perf. 2024-03-13 20:07:27 -04:00
comfyanonymous
eda8704386 Add SamplerDPMPP_3M_SDE node. 2024-03-12 12:16:37 -04:00